Seedance 2.5

ByteDance Seedance 2.5 — next-generation async video generation. Coming soon to reAPI. This page is a preview seeded from the current Seedance generation; final parameters and pricing land at launch.

Coming soon. The Seedance 2.5 API is not available yet. The endpoint, parameters, and pricing below are a preview seeded from the current Seedance generation and may change when the model ships. Watch the model page for launch.

ByteDance's next-generation async video model, coming to reAPI. Seedance 2.5 turns text, photos, clips, or audio into short video. Like the current Seedance family, mode is implicit: which media fields you set (prompt, image_urls, image_with_roles, video_urls, audio_urls) decides whether the request runs as text-to-video, image-to-video, first/last-frame transition, or reference-driven generation. See pricing on the model page.

Status

Seedance 2.5 is coming soon. This documentation is a preview so you can plan an integration ahead of launch. When the model ships:

The model ids, full parameter set, constraints, and per-second rates are finalized here.
The playground on the model page becomes live.
This banner is removed.

The shape below mirrors the current Seedance generation. Treat every field as provisional until launch.

Quick example (preview)

curl https://reapi.ai/api/v1/videos/generations \
  -H "Authorization: Bearer YOUR_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "seedance-2.5",
    "prompt": "A kitten yawning at the camera, cinematic warm tones",
    "resolution": "720p",
    "size": "16:9",
    "duration": 5
  }'

import requests

resp = requests.post(
    "https://reapi.ai/api/v1/videos/generations",
    headers={
        "Authorization": "Bearer YOUR_API_KEY",
        "Content-Type": "application/json",
    },
    json={
        "model": "seedance-2.5",
        "prompt": "A kitten yawning at the camera, cinematic warm tones",
        "resolution": "720p",
        "size": "16:9",
        "duration": 5,
    },
    timeout=30,
)
print(resp.json())

const r = await fetch("https://reapi.ai/api/v1/videos/generations", {
  method: "POST",
  headers: {
    Authorization: "Bearer YOUR_API_KEY",
    "Content-Type": "application/json",
  },
  body: JSON.stringify({
    model: "seedance-2.5",
    prompt: "A kitten yawning at the camera, cinematic warm tones",
    resolution: "720p",
    size: "16:9",
    duration: 5,
  }),
});
console.log(await r.json());

package main

import (
    "bytes"
    "encoding/json"
    "fmt"
    "io"
    "net/http"
)

func main() {
    body, _ := json.Marshal(map[string]any{
        "model":      "seedance-2.5",
        "prompt":     "A kitten yawning at the camera, cinematic warm tones",
        "resolution": "720p",
        "size":       "16:9",
        "duration":   5,
    })
    req, _ := http.NewRequest("POST",
        "https://reapi.ai/api/v1/videos/generations", bytes.NewReader(body))
    req.Header.Set("Authorization", "Bearer YOUR_API_KEY")
    req.Header.Set("Content-Type", "application/json")

    resp, _ := http.DefaultClient.Do(req)
    defer resp.Body.Close()
    out, _ := io.ReadAll(resp.Body)
    fmt.Println(string(out))
}

These calls will return 404 model not found until Seedance 2.5 launches.

Authentication

Every call needs a Bearer token. Generate keys at reapi.ai/settings/apikeys.

Authorization: Bearer YOUR_API_KEY

Keys carry the active workspace's billing scope — there is no separate project header.

Endpoint

POST /api/v1/videos/generations
GET  /api/v1/tasks/{id}

Submission is async. The POST returns immediately with a task_id; the task endpoint returns the same envelope until completion. Polling does not consume credits.

Variants (preview)

Seedance 2.5 is expected to ship as a family of variants sharing one parameter shape, picked via model:

Variant	Speed	1080p	Real-person uploads
`seedance-2.5`	standard	✅	—
`seedance-2.5-fast`	faster	❌ (480p / 720p only)	—
`seedance-2.5-face`	standard	✅	✅
`seedance-2.5-fast-face`	faster	❌ (480p / 720p only)	✅

reAPI never silently substitutes one variant for another. Final variant ids are confirmed at launch.

Request body (preview)

Mode is implicit — which media fields you set decides text-to-video, image-to-video, first/last-frame, or reference-driven generation.

Field	Type	Default	Notes
`model`	string	—	One of the variants above. Required.
`prompt`	string	—	Describe the video. Optional when a reference field carries content.
`duration`	integer	`5`	Output length in seconds, `4`–`15`.
`size`	string	`16:9`	`16:9` / `9:16` / `1:1` / `4:3` / `3:4` / `21:9` / `adaptive`.
`resolution`	string	`480p`	`480p` / `720p` / `1080p`. `1080p` on standard / face variants only.
`seed`	integer	—	Reproducibility hint.
`generate_audio`	boolean	`false`	Synthesize an audio track to play with the video.
`return_last_frame`	boolean	`false`	Return `output.last_frame_url` for continuous chaining.
`tools`	object[]	—	`[{ "type": "web_search" }]` to let the model query the web.
`image_urls`	string[]	—	Up to 9 reference images (image-to-video). Public HTTP(S) URLs.
`image_with_roles`	object[]	—	First / last frame interpolation (`{ url, role }`).
`video_urls`	string[]	—	Up to 3 reference clips, combined ≤ 15s.
`audio_urls`	string[]	—	Up to 3 reference audio tracks for lip-sync.

No data: URIs. reAPI rejects base64 inputs platform-wide — every URL field must be a public HTTP(S) URL. Upload to your own object storage (S3, R2, OSS, …) and pass the URL.

Response envelope

Submit and poll share the same shape — only status and output fill in over time.

{
  "id": "task_018f5a3a1b6e7d9f8c2b4d6e8f0a2c4e",
  "model": "seedance-2.5",
  "status": "completed",
  "created_at": 1735000000,
  "output": {
    "video_urls": ["https://cdn.reapi.ai/media/tasks/.../0.mp4"],
    "last_frame_url": "https://cdn.reapi.ai/media/tasks/.../0.png"
  },
  "error": null
}

Poll GET /api/v1/tasks/{id} (see the Tasks reference) until status === "completed". output.video_urls holds the generated MP4 URL. output.last_frame_url is present when the request set return_last_frame: true.

Pricing

Seedance 2.5 will bill per-second, scaled by resolution and reference mode — the same dimensions as the current Seedance family:

credits = ceil(per_second_usd × billable_seconds × 1000)

where 1 credit = $0.001. Final per-second rates are published on the model page at launch — that table is dynamic and always reflects the current rate. Failed jobs are refunded automatically.

Status

Seedance 2.5 is coming soon. This documentation is a preview so you can plan an integration ahead of launch. When the model ships:

The model ids, full parameter set, constraints, and per-second rates are finalized here.
The playground on the model page becomes live.
This banner is removed.

The shape below mirrors the current Seedance generation. Treat every field as provisional until launch.

Quick example (preview)

curl https://reapi.ai/api/v1/videos/generations \
  -H "Authorization: Bearer YOUR_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "seedance-2.5",
    "prompt": "A kitten yawning at the camera, cinematic warm tones",
    "resolution": "720p",
    "size": "16:9",
    "duration": 5
  }'

import requests

resp = requests.post(
    "https://reapi.ai/api/v1/videos/generations",
    headers={
        "Authorization": "Bearer YOUR_API_KEY",
        "Content-Type": "application/json",
    },
    json={
        "model": "seedance-2.5",
        "prompt": "A kitten yawning at the camera, cinematic warm tones",
        "resolution": "720p",
        "size": "16:9",
        "duration": 5,
    },
    timeout=30,
)
print(resp.json())

const r = await fetch("https://reapi.ai/api/v1/videos/generations", {
  method: "POST",
  headers: {
    Authorization: "Bearer YOUR_API_KEY",
    "Content-Type": "application/json",
  },
  body: JSON.stringify({
    model: "seedance-2.5",
    prompt: "A kitten yawning at the camera, cinematic warm tones",
    resolution: "720p",
    size: "16:9",
    duration: 5,
  }),
});
console.log(await r.json());

package main

import (
    "bytes"
    "encoding/json"
    "fmt"
    "io"
    "net/http"
)

func main() {
    body, _ := json.Marshal(map[string]any{
        "model":      "seedance-2.5",
        "prompt":     "A kitten yawning at the camera, cinematic warm tones",
        "resolution": "720p",
        "size":       "16:9",
        "duration":   5,
    })
    req, _ := http.NewRequest("POST",
        "https://reapi.ai/api/v1/videos/generations", bytes.NewReader(body))
    req.Header.Set("Authorization", "Bearer YOUR_API_KEY")
    req.Header.Set("Content-Type", "application/json")

    resp, _ := http.DefaultClient.Do(req)
    defer resp.Body.Close()
    out, _ := io.ReadAll(resp.Body)
    fmt.Println(string(out))
}

These calls will return 404 model not found until Seedance 2.5 launches.

Authentication

Every call needs a Bearer token. Generate keys at reapi.ai/settings/apikeys.

Authorization: Bearer YOUR_API_KEY

Keys carry the active workspace's billing scope — there is no separate project header.

Endpoint

POST /api/v1/videos/generations
GET  /api/v1/tasks/{id}

Submission is async. The POST returns immediately with a task_id; the task endpoint returns the same envelope until completion. Polling does not consume credits.

Variants (preview)

Seedance 2.5 is expected to ship as a family of variants sharing one parameter shape, picked via model:

Variant	Speed	1080p	Real-person uploads
`seedance-2.5`	standard	✅	—
`seedance-2.5-fast`	faster	❌ (480p / 720p only)	—
`seedance-2.5-face`	standard	✅	✅
`seedance-2.5-fast-face`	faster	❌ (480p / 720p only)	✅

reAPI never silently substitutes one variant for another. Final variant ids are confirmed at launch.

Request body (preview)

Mode is implicit — which media fields you set decides text-to-video, image-to-video, first/last-frame, or reference-driven generation.

Field	Type	Default	Notes
`model`	string	—	One of the variants above. Required.
`prompt`	string	—	Describe the video. Optional when a reference field carries content.
`duration`	integer	`5`	Output length in seconds, `4`–`15`.
`size`	string	`16:9`	`16:9` / `9:16` / `1:1` / `4:3` / `3:4` / `21:9` / `adaptive`.
`resolution`	string	`480p`	`480p` / `720p` / `1080p`. `1080p` on standard / face variants only.
`seed`	integer	—	Reproducibility hint.
`generate_audio`	boolean	`false`	Synthesize an audio track to play with the video.
`return_last_frame`	boolean	`false`	Return `output.last_frame_url` for continuous chaining.
`tools`	object[]	—	`[{ "type": "web_search" }]` to let the model query the web.
`image_urls`	string[]	—	Up to 9 reference images (image-to-video). Public HTTP(S) URLs.
`image_with_roles`	object[]	—	First / last frame interpolation (`{ url, role }`).
`video_urls`	string[]	—	Up to 3 reference clips, combined ≤ 15s.
`audio_urls`	string[]	—	Up to 3 reference audio tracks for lip-sync.

No data: URIs. reAPI rejects base64 inputs platform-wide — every URL field must be a public HTTP(S) URL. Upload to your own object storage (S3, R2, OSS, …) and pass the URL.

Response envelope

Submit and poll share the same shape — only status and output fill in over time.

{
  "id": "task_018f5a3a1b6e7d9f8c2b4d6e8f0a2c4e",
  "model": "seedance-2.5",
  "status": "completed",
  "created_at": 1735000000,
  "output": {
    "video_urls": ["https://cdn.reapi.ai/media/tasks/.../0.mp4"],
    "last_frame_url": "https://cdn.reapi.ai/media/tasks/.../0.png"
  },
  "error": null
}

Pricing

Seedance 2.5 will bill per-second, scaled by resolution and reference mode — the same dimensions as the current Seedance family:

credits = ceil(per_second_usd × billable_seconds × 1000)

where 1 credit = $0.001. Final per-second rates are published on the model page at launch — that table is dynamic and always reflects the current rate. Failed jobs are refunded automatically.

Seedance 2.5

Status

Quick example (preview)

Authentication

Endpoint

Variants (preview)

Request body (preview)

Response envelope

Pricing

Table of Contents

Seedance 2.5

Status

Quick example (preview)

Authentication

Endpoint

Variants (preview)

Request body (preview)

Response envelope

Pricing

Table of Contents